AI技术在儿童肺结核影像诊断中的研究现状与展望

doi:10.19871/j.cnki.xfcrbzz.2023.06.015

摘要/Abstract

摘要： 肺结核是肆虐全球的传染性疾病之一,儿童肺结核也依旧是关系我国儿童、青少年公共健康的重要议题。由于儿童肺结核在临床诊断上缺乏特异性,其早期筛查及诊断具有一定的难度。胸部影像诊断被认为是结核病诊断的有效途径,在儿童肺结核管控中也具有较高的应用价值。近年来,AI技术飞速发展,在医疗领域中的应用也取得了令人瞩目的成效,特别是在大数据处理、降低人力成本、提高临床效能方面作用明显。AI与医学影像的结合模式也逐步应用到了肺结核筛查及诊断中,多种基于影像学检查、以肺结核筛查及诊断为目的的AI算法、软件及诊疗系统应运而生。然而,以往的相关研究多以成人肺结核为主,在儿童肺结核方面缺乏足够的报道。本文客观总结了近年来AI技术在肺结核、儿童肺结核影像诊断中的研究及应用现状,并就其在儿童肺结核领域中的局限性及未来展望进行综述,望日后相应的AI技术开发能更加关注儿童病例。

关键词: 肺结核, 儿童, 人工智能, 影像诊断

Abstract: Tuberculosis remains one of the most prevalent infectious diseases globally, and pediatric tuberculosis continues to be an important issue for the public health of children and adolescents in our country. Due to the lack of specificity in the clinical diagnosis of pediatric tuberculosis, early screening and diagnosis pose certain challenges. Chest imaging diagnosis is considered a practical approach to tuberculosis diagnosis and has high utility in controlling pediatric pulmonary tuberculosis. In recent years, artificial intelligence (AI) technology has rapidly developed and achieved remarkable results in the medical field, particularly in big data processing, reducing manpower costs, and improving clinical efficiency. The integration of AI and medical imaging has gradually been applied to tuberculosis screening and diagnosis, leading to various AI algorithms, software, and diagnostic systems aimed at tuberculosis screening and diagnosis using imaging examinations. Previous studies have mainly focused on adult tuberculosis, with insufficient reports and attention given to pediatric pulmonary tuberculosis. This article primarily summarizes the research and application status of AI technology in the imaging diagnosis of tuberculosis and pediatric pulmonary tuberculosis in recent years and provides an overview of its limitations and future prospects in the field of pediatric pulmonary tuberculosis. It is hoped that future AI development research will pay more attention to children's cases.

Key words: Pulmonary tuberculosis, Pediatric, Artificial intelligence, Imaging diagnosis

中图分类号:

R445
R529.9

罗梵, 张娜, 李晨曦. AI技术在儿童肺结核影像诊断中的研究现状与展望[J]. 新发传染病电子杂志, 2023, 8(6): 79-83.

Luo Fan, Zhang Na, Li Chenxi. Research status and prospect of artificial intelligence technology in imaging diagnosis of pediatric pulmonary tuberculosis[J]. Electronic Journal of Emerging Infectious Diseases, 2023, 8(6): 79-83.

参考文献

[1] 宋敏, 陆普选, 方伟军, 等. 2022年WHO全球结核病报告:全球与中国关键数据分析[J/CD]. 新发传染病电子杂志, 2023, 8(1): 87-92.
[2] BAGCCHI S.WHO's Global Tuberculosis Report 2022[J]. Lancet Microbe, 2023, 4(1): e20.
[3] 李蒙, 高谦. 结核病自然史的阶段划分及其诊断的现状与展望[J]. 中国防痨杂志, 2021, 43(11): 1125-1131.
[4] NAIDOO J, SHELMERDINE SC, CHARCAPE CFU, et al.Artificial Intelligence in Paediatric Tuberculosis[J]. Pediatr Radiol, 2023, 53(9):1733-1745.
[5] SODHI K, BHALLA A, MAHOMED N, et al.Imaging of thoracic tuberculosis in children: current and future directions[J]. Pediatr Radiol, 2017, 47(10): 1260-1268.
[6] MANSON D.MR imaging of the chest in children[J]. Acta Radiol, 2013, 54(9): 1075-1085.
[7] SODHI K, SHARMA M, SAXENA A, et al.MRI in Thoracic Tuberculosis of Children[J]. Indian J Pediatr, 2017, 84(9): 670-676.
[8] PEPRAH K, ANDRONIKOU S, GOUSSARD P.Characteristic magnetic resonance imaging low T2 signal intensity of necrotic lung parenchyma in children with pulmonary tuberculosis[J]. J Thorac Imaging, 2012, 27(3): 171-174.
[9] SODHI K, CIET P, VASANAWALA S, et al.Practical protocol for lung magnetic resonance imaging and common clinical indications[J]. Pediatr Radiol, 2022, 52(2): 295-311.
[10] CONCEPCION N, LAYA B, ANDRONIKOU S, et al.Imaging recommendations and algorithms for pediatric tuberculosis: part 1-thoracic tuberculosis[J]. Pediatr Radiol, 2023, 53(9): 1773-1781.
[11] JAEGER S, KARARGYRIS A, CANDEMIR S, et al.Automatic screening for tuberculosis in chest radiographs: a survey[J]. Quant Imaging Med Surg, 2013, 3(2): 89-99.
[12] 马依迪丽•尼加提,阿里木江•阿卜杜凯尤木,米日古丽•达毛拉,等.基于人工智能肺结核筛查技术在基层医院影像诊断中的应用价值[J/CD].新发传染病电子杂志,2021,6(2):137-141.
[13] LURE FYM, JAEGER S, ANTANI S, 等. 自动化显微镜检测和数字化胸片诊断系统在肺结核筛查中的应用[J/CD]. 新发传染病电子杂志, 2017,2(1):5-9.
[14] ZAIDI S, HABIB S, VAN GINNEKEN B, et al.Evaluation of the diagnostic accuracy of Computer-Aided Detection of tuberculosis on Chest radiography among private sector patients in Pakistan[J]. Sci Rep, 2018, 8(1): 12339.
[15] RAHMAN M, CODLIN A, RAHMAN M, et al.An evaluation of automated chest radiography reading software for tuberculosis screening among public- and private-sector patients[J]. Eur Respir J, 2017, 49(5): 1602159
[16] XU T, CHENG I, LONG R, et al.Novel coarse-to-fine dual scale technique for tuberculosis cavity detection in chest radiographs[J]. EURASIP Journal on Image and Video Processing, 2013, 2013(1): 3.
[17] MELENDEZ J, HOGEWEG L, SÁNCHEZ CI, et al. Accuracy of an automated system for tuberculosis detection on chest radiographs in high-risk screening[J]. Int J Tuberc Lung Dis, 2018, 22(5):567-571.
[18] JAEGER S, KARARGYRIS A, ANTANI S, et al.Detecting tuberculosis in radiographs using combined lung masks[J]. Annu Int Conf IEEE Eng Med Biol Soc, 2012, 2012: 4978-4981.
[19] MOUTON A, PITCHER R, DOUGLAS T.Computer-aided detection of pulmonary pathology in pediatric chest radiographs[J]. Med Image Comput Comput Assist Interv, 2010, 13(pt3):619-625.
[20] PALMER M, SEDDON J, VAN DER ZALM M, et al. Optimising computer aided detection to identify intra-thoracic tuberculosis on chest x-ray in South African children[J]. PLOS Glob Public Health, 2023, 3(5): e0001799.
[21] KULKARNI S, JHA S. Artificial Intelligence, Radiology, and Tuberculosis: A Review[J]. Acad Radiol, 2020, 27(1): 71-75.
[22] NGIAM K, KHOR I.Big data and machine learning algorithms for health-care delivery[J]. Lancet Oncol, 2019, 20(5): e262-e273.
[23] LAKHANI P, SUNDARAM B.Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks[J]. Radiology, 2017, 284(2): 574-582.
[24] SANTOSH K, ALLU S, RAJARAMAN S, et al.Advances in Deep Learning for Tuberculosis Screening using Chest X-rays: The Last 5 Years Review[J]. J Med Syst, 2022, 46(11): 82.
[25] 单连峰, 郭芳. 基于深度学习卷积神经网络的肺结核CT辅助诊断模型在临床中的应用价值[J]. 中国新通信, 2022, 24(24): 126-128.
[26] 闫明艳,陈根铭, 赖超, 等. 人工智能对肺结核患者病变检出及定性诊断价值研究 [J/CD]. 新发传染病电子杂志, 2018, 3(4): 214-217.
[27] MA L, WANG Y, GUO L, et al.Developing and verifying automatic detection of active pulmonary tuberculosis from multi-slice spiral CT images based on deep learning[J]. J Xray Sci Technol, 2020, 28(5): 939-951.
[28] SCHALEKAMP S, KLEIN W, VAN LEEUWEN K.Current and emerging artificial intelligence applications in chest imaging: a pediatric perspective[J].Pediatr Radiol, 2022, 52(11): 2120-2130.
[29] KIM Y, PARK J, HWANG E, et al.Applications of artificial intelligence in the thorax: a narrative review focusing on thoracic radiology[J]. J Thorac Dis, 2021, 13(12): 6943-6962.